Privacy-preserving object detection with poisoning recognition for autonomous vehicles
J Li, W Guo, L Xie, X Liu, J Cai - IEEE Transactions on Network …, 2022 - ieeexplore.ieee.org
Object detection has achieved significant progress in attaining high-quality performance
without leaking private messages. However, traditional approaches cannot defend the …
without leaking private messages. However, traditional approaches cannot defend the …
The Necessity of AI Audit Standards Boards
Auditing of AI systems is a promising way to understand and manage ethical problems and
societal risks associated with contemporary AI systems, as well as some anticipated future …
societal risks associated with contemporary AI systems, as well as some anticipated future …
Scaling Model Checking for DNN Analysis via State-Space Reduction and Input Segmentation (Extended Version)
Owing to their remarkable learning capabilities and performance in real-world applications,
the use of machine learning systems based on Neural Networks (NNs) has been …
the use of machine learning systems based on Neural Networks (NNs) has been …
Considering the Impact of Noise on Machine Learning Accuracy
Modern day smart cyber-physical systems (CPS) and Internet of Things (IoTs), including
those deployed in critical devices such as wearables, often use embedded machine …
those deployed in critical devices such as wearables, often use embedded machine …
[PDF][PDF] Robust computing for machine learning-based systems
Machine learning (ML) has emerged as the principal tool for performing complex tasks
which are impractical (if not impossible) to code by humans. ML techniques provide …
which are impractical (if not impossible) to code by humans. ML techniques provide …
A Deep Dive into Deep Learning-Based Adversarial Attacks and Defenses in Computer Vision: From a Perspective of Cybersecurity
B Vineetha, J Suryaprasad, SS Shylaja… - … conference on WorldS4, 2023 - Springer
Adversarial attacks are deliberate data manipulations that may appear harmless to the
viewer yet lead to incorrect categorization in a machine learning or deep learning system …
viewer yet lead to incorrect categorization in a machine learning or deep learning system …
(Un) Trustworthy Machine Learning
E Bagdasaryan - 2023 - search.proquest.com
Abstract Machine learning methods have become a commodity in the toolkits of both
researchers and practitioners. For performance and privacy reasons, new applications often …
researchers and practitioners. For performance and privacy reasons, new applications often …
Towards security by design of connected and automated vehicles: cyber and physical threats, mitigations, and architectures
D Suo - 2021 - dspace.mit.edu
This thesis proposes a security by design framework for identifying and mitigating cyber and
physical threats on CAVs. A structured security engineering process for threat identification …
physical threats on CAVs. A structured security engineering process for threat identification …
[PDF][PDF] Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead
M SHAFIQUE - arxiv.org
ABSTRACT Currently, Machine Learning (ML) is becoming ubiquitous in everyday life. Deep
Learning (DL) is already present in many applications ranging from computer vision for …
Learning (DL) is already present in many applications ranging from computer vision for …
Fast and Efficient Decision-Based Attack for Deep Neural Network on Edge
H Jain, S Rathore, TPA Rahoof… - … IEEE Workshop on …, 2020 - ieeexplore.ieee.org
Deep Neural Networks (DNN) are very effective in high performance applications such as
computer vision, natural language processing and speech recognition. However, these …
computer vision, natural language processing and speech recognition. However, these …